Skip to main navigation Skip to search Skip to main content

Analysis of Deep Learning Libraries: Keras, PyTorch, and MXnet

  • Georgia Southern University

Research output: Contribution to book or proceedingConference articlepeer-review

36 Scopus citations

Abstract

As many artificial neural libraries are developing the deep learning algorithm and implementing it became accessible to anyone. This study points out the disparity of performance in deep learning models such as convolutional neural networks (CNN) when implemented with different artificial neural libraries. Libraries such as Keras, Pytorch, and MXnet was utilized for each three CNN model then binary image classification was done based on the Dogs vs. Cats dataset from Kaggle. With using 75% of the dataset as the training set and the rest of 25% as a testing set, and as a result, each CNN model gave a different F1 score value and accuracy.

Original languageEnglish
Title of host publication2022 IEEE/ACIS 20th International Conference on Software Engineering Research, Management and Applications, SERA 2022
EditorsJuyeon Jo, Yeong-Tae Song, Lin Deng, Junghwan Rhee
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages54-62
Number of pages9
ISBN (Electronic)9781665483506
ISBN (Print)9781665483506
DOIs
StatePublished - Jun 30 2022
Event20th IEEE/ACIS International Conference on Software Engineering Research, Management and Applications, SERA 2022 - Las Vegas, United States
Duration: May 25 2022May 27 2022

Publication series

Name2022 IEEE/ACIS 20th International Conference on Software Engineering Research, Management and Applications, SERA 2022

Conference

Conference20th IEEE/ACIS International Conference on Software Engineering Research, Management and Applications, SERA 2022
Country/TerritoryUnited States
CityLas Vegas
Period05/25/2205/27/22

Scopus Subject Areas

  • Management of Technology and Innovation
  • Computer Networks and Communications
  • Computer Science Applications
  • Software
  • Safety, Risk, Reliability and Quality

Keywords

  • artificial neural network
  • Binary image classification
  • CNN
  • Keras
  • MXnet
  • Pytorch

Fingerprint

Dive into the research topics of 'Analysis of Deep Learning Libraries: Keras, PyTorch, and MXnet'. Together they form a unique fingerprint.

Cite this